RESUMEN
BACKGROUND: The average sensitivity of conventional cytology for the identification of cancer cells in effusion specimens is only approximately 58%. DNA image cytometry (DNA-ICM), which exploits the DNA content of morphologically suspicious nuclei measured on digital images, has a sensitivity of up to 91% for the detection of cancer cells. However, when performed manually, to our knowledge to date, an expert needs approximately 60 minutes for the analysis of a single slide. METHODS: In the current study, the authors present a novel method of supervised machine learning for the automated identification of morphologically suspicious mesothelial and epithelial nuclei in Feulgen-stained effusion specimens. The authors compared this with manual DNA-ICM and a gold standard cytological diagnosis for 121 cases. Furthermore, the authors retrospectively analyzed whether the amount of morphometrically abnormal mesothelial or epithelial nuclei detected by the digital classifier could be used as an additional diagnostic marker. RESULTS: The presented semiautomated DNA karyometric solution identified more diagnostically relevant abnormal nuclei compared with manual DNA-ICM, which led to a higher sensitivity (76.4% vs 68.5%) at a specificity of 100%. The ratio between digitally abnormal and all mesothelial nuclei was found to identify cancer cell-positive slides at 100% sensitivity and 70% specificity. The time effort for an expert therefore is reduced to the verification of a few nuclei with exceeding DNA content, which to our knowledge can be accomplished within 5 minutes. CONCLUSIONS: The authors have created and validated a computer-assisted bimodal karyometric approach for which both nuclear morphology and DNA are quantified from a Feulgen-stained slide. DNA karyometry thus increases the diagnostic accuracy and reduces the workload of an expert when compared with manual DNA-ICM.
Asunto(s)
Aneuploidia , Núcleo Celular/patología , Cariometría/métodos , Aprendizaje Automático , Neoplasias/patología , ADN de Neoplasias/aislamiento & purificación , Diagnóstico por Computador/métodos , Epitelio/patología , Humanos , Citometría de Imagen/métodos , Cariometría/normas , Neoplasias/genética , Sensibilidad y EspecificidadRESUMEN
BACKGROUND: Virtual microscopy and automated processing of cytological slides are more challenging compared to histological slides. Since cytological slides exhibit a three-dimensional surface and the required microscope objectives with high resolution have a low depth of field, these cannot capture all objects of a single field of view in focus. One solution would be to scan multiple focal planes; however, the increase in processing time and storage requirements are often prohibitive for clinical routine. MATERIALS AND METHODS: In this paper, we show that it is a reasonable trade-off to scan a single focal plane and automatically reject defocused objects from the analysis. To this end, we have developed machine learning solutions for the automated identification of defocused objects. Our approach includes creating novel features, systematically optimizing their parameters, selecting adequate classifier algorithms, and identifying the correct decision boundary between focused and defocused objects. We validated our approach for computer-assisted DNA image cytometry. RESULTS AND CONCLUSIONS: We reach an overall sensitivity of 96.08% and a specificity of 99.63% for identifying defocused objects. Applied on ninety cytological slides, the developed classifiers automatically removed 2.50% of the objects acquired during scanning, which otherwise would have interfered the examination. Even if not all objects are acquired in focus, computer-assisted DNA image cytometry still identified more diagnostically or prognostically relevant objects compared to manual DNA image cytometry. At the same time, the workload for the expert is reduced dramatically.
RESUMEN
BACKGROUND: This report describes what to the authors' knowledge is the first clinical application of semiautomated multimodal cell analysis (MMCA), a novel technique for the early detection of cancer for cases with a limited number of suspicious cells. In this clinical study, MMCA was applied to oral cancer diagnostics on brush biopsies. The MMCA approach was based on the sequential application of multiple stainings of identical, slide-based cells and repeated relocalizations and measurements of their diagnostic features, resulting in multiparametric features of individual cells. Data integration of the variously stained cells increased diagnostic accuracy. The implementation of MMCA also enabled fully automatic, adaptive image preprocessing, including registration of multimodal images and segmentation of cell nuclei. METHODS: In a preliminary clinical trial, 47 slides from brush biopsies of suspicious oral lesions were analyzed. The final histologic diagnoses included 20 squamous cell carcinomas, 7 hyperkeratotic leukoplakias, and 20 lichen planus mucosae. RESULTS: The stepwise application of 2 additional approaches (morphology, DNA content, argyrophilic nucleolar organizer region counts) increased the specificity of conventional cytologic diagnosis from 92.6% to 100%. This feasibility study provided a proof of concept, demonstrating efficiency, robustness, and diagnostic accuracy on slide-based cytologic specimens. CONCLUSIONS: The authors concluded that MMCA may become a sensitive and highly specific, objective, and reproducible adjuvant diagnostic tool for the identification of neoplastic changes in oral smears that contain only a few abnormal cells.
Asunto(s)
Biopsia/métodos , Carcinoma de Células Escamosas/patología , Neoplasias de la Boca/patología , Adulto , Anciano , Anciano de 80 o más Años , Antígenos Nucleares/análisis , Carcinoma de Células Escamosas/genética , Carcinoma de Células Escamosas/metabolismo , ADN de Neoplasias/análisis , ADN de Neoplasias/genética , Diagnóstico Precoz , Humanos , Citometría de Imagen/métodos , Persona de Mediana Edad , Mucosa Bucal/metabolismo , Mucosa Bucal/patología , Neoplasias de la Boca/genética , Neoplasias de la Boca/metabolismo , Región Organizadora del Nucléolo/química , Reproducibilidad de los Resultados , Sensibilidad y Especificidad , Tinción con Nitrato de PlataRESUMEN
The paper describes the key component of the Multimodal Cell Analysis approach, a novel cytologic evaluation method for early cancer detection. The approach is based on repeated staining of a cell smear. The correlation of features and data extracted from the different stains, and related to relocated individual cells, may yield a dramatic increase of diagnostic reliability. In order to utilise the technique, fully automatic, adaptive image preprocessing techniques need to be applied, which are described in this article: coregistration of multimodal images, segmentation, and classification of cell nuclei. The presented feasibility study shows both efficiency and robustness of all steps being high regarding medical image material, and it strongly supports clinical application.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Neoplasias/patología , Coloración y Etiquetado , Núcleo Celular/ultraestructura , Citodiagnóstico , Estudios de Factibilidad , Humanos , Microscopía/métodos , Neoplasias/diagnóstico , Neoplasias/ultraestructura , Reconocimiento de Normas Patrones AutomatizadasRESUMEN
The paper describes the key component of the Multimodal Cell Analysis approach, a novel cytologic evaluation method for early cancer detection. The approach is based on a repeated staining of a cell smear. The correlation of features and data extracted from different stainings, and related to relocated individual cells, will yield a dramatic increase of diagnostic reliability. The necessary fully automatic preprocessing steps are presented: coregistration of multimodal images, segmentation, and classification of cell nuclei. Both efficiency and robustness of all steps reached at the current stage of research, are high regarding medical image material, and strongly support clinical application.